diff options
Diffstat (limited to 'arch/s390/kvm/priv.c')
| -rw-r--r-- | arch/s390/kvm/priv.c | 191 |
1 files changed, 115 insertions, 76 deletions
diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c index ed52ffa8d5d4..3335fa09b6f1 100644 --- a/arch/s390/kvm/priv.c +++ b/arch/s390/kvm/priv.c @@ -2,7 +2,7 @@ /* * handling privileged instructions * - * Copyright IBM Corp. 2008, 2018 + * Copyright IBM Corp. 2008, 2020 * * Author(s): Carsten Otte <cotte@de.ibm.com> * Christian Borntraeger <borntraeger@de.ibm.com> @@ -11,8 +11,8 @@ #include <linux/kvm.h> #include <linux/gfp.h> #include <linux/errno.h> -#include <linux/compat.h> #include <linux/mm_types.h> +#include <linux/pgtable.h> #include <asm/asm-offsets.h> #include <asm/facility.h> @@ -20,9 +20,7 @@ #include <asm/debug.h> #include <asm/ebcdic.h> #include <asm/sysinfo.h> -#include <asm/pgtable.h> #include <asm/page-states.h> -#include <asm/pgalloc.h> #include <asm/gmap.h> #include <asm/io.h> #include <asm/ptrace.h> @@ -103,7 +101,20 @@ static int handle_set_clock(struct kvm_vcpu *vcpu) return kvm_s390_inject_prog_cond(vcpu, rc); VCPU_EVENT(vcpu, 3, "SCK: setting guest TOD to 0x%llx", gtod.tod); - kvm_s390_set_tod_clock(vcpu->kvm, >od); + /* + * To set the TOD clock the kvm lock must be taken, but the vcpu lock + * is already held in handle_set_clock. The usual lock order is the + * opposite. As SCK is deprecated and should not be used in several + * cases, for example when the multiple epoch facility or TOD clock + * steering facility is installed (see Principles of Operation), a + * slow path can be used. If the lock can not be taken via try_lock, + * the instruction will be retried via -EAGAIN at a later point in + * time. + */ + if (!kvm_s390_try_set_tod_clock(vcpu->kvm, >od)) { + kvm_s390_retry_instr(vcpu); + return -EAGAIN; + } kvm_s390_set_psw_cc(vcpu, 0); return 0; @@ -270,18 +281,18 @@ static int handle_iske(struct kvm_vcpu *vcpu) return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING); retry: unlocked = false; - down_read(¤t->mm->mmap_sem); + mmap_read_lock(current->mm); rc = get_guest_storage_key(current->mm, vmaddr, &key); if (rc) { - rc = fixup_user_fault(current, current->mm, vmaddr, + rc = fixup_user_fault(current->mm, vmaddr, FAULT_FLAG_WRITE, &unlocked); if (!rc) { - up_read(¤t->mm->mmap_sem); + mmap_read_unlock(current->mm); goto retry; } } - up_read(¤t->mm->mmap_sem); + mmap_read_unlock(current->mm); if (rc == -EFAULT) return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING); if (rc < 0) @@ -317,17 +328,17 @@ static int handle_rrbe(struct kvm_vcpu *vcpu) return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING); retry: unlocked = false; - down_read(¤t->mm->mmap_sem); + mmap_read_lock(current->mm); rc = reset_guest_reference_bit(current->mm, vmaddr); if (rc < 0) { - rc = fixup_user_fault(current, current->mm, vmaddr, + rc = fixup_user_fault(current->mm, vmaddr, FAULT_FLAG_WRITE, &unlocked); if (!rc) { - up_read(¤t->mm->mmap_sem); + mmap_read_unlock(current->mm); goto retry; } } - up_read(¤t->mm->mmap_sem); + mmap_read_unlock(current->mm); if (rc == -EFAULT) return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING); if (rc < 0) @@ -385,19 +396,21 @@ static int handle_sske(struct kvm_vcpu *vcpu) if (kvm_is_error_hva(vmaddr)) return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING); - down_read(¤t->mm->mmap_sem); + mmap_read_lock(current->mm); rc = cond_set_guest_storage_key(current->mm, vmaddr, key, &oldkey, m3 & SSKE_NQ, m3 & SSKE_MR, m3 & SSKE_MC); if (rc < 0) { - rc = fixup_user_fault(current, current->mm, vmaddr, + rc = fixup_user_fault(current->mm, vmaddr, FAULT_FLAG_WRITE, &unlocked); rc = !rc ? -EAGAIN : rc; } - up_read(¤t->mm->mmap_sem); + mmap_read_unlock(current->mm); if (rc == -EFAULT) return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING); + if (rc == -EAGAIN) + continue; if (rc < 0) return rc; start += PAGE_SIZE; @@ -429,7 +442,7 @@ static int handle_ipte_interlock(struct kvm_vcpu *vcpu) vcpu->stat.instruction_ipte_interlock++; if (psw_bits(vcpu->arch.sie_block->gpsw).pstate) return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); - wait_event(vcpu->kvm->arch.ipte_wq, !ipte_lock_held(vcpu)); + wait_event(vcpu->kvm->arch.ipte_wq, !ipte_lock_held(vcpu->kvm)); kvm_s390_retry_instr(vcpu); VCPU_EVENT(vcpu, 4, "%s", "retrying ipte interlock operation"); return 0; @@ -611,6 +624,7 @@ static int handle_io_inst(struct kvm_vcpu *vcpu) static int handle_pqap(struct kvm_vcpu *vcpu) { struct ap_queue_status status = {}; + crypto_hook pqap_hook; unsigned long reg0; int ret; uint8_t fc; @@ -626,10 +640,12 @@ static int handle_pqap(struct kvm_vcpu *vcpu) * available for the guest are AQIC and TAPQ with the t bit set * since we do not set IC.3 (FIII) we currently will only intercept * the AQIC function code. + * Note: running nested under z/VM can result in intercepts for other + * function codes, e.g. PQAP(QCI). We do not support this and bail out. */ reg0 = vcpu->run->s.regs.gprs[0]; fc = (reg0 >> 24) & 0xff; - if (WARN_ON_ONCE(fc != 0x03)) + if (fc != 0x03) return -EOPNOTSUPP; /* PQAP instruction is allowed for guest kernel only */ @@ -653,18 +669,20 @@ static int handle_pqap(struct kvm_vcpu *vcpu) return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); /* - * Verify that the hook callback is registered, lock the owner - * and call the hook. + * If the hook callback is registered, there will be a pointer to the + * hook function pointer in the kvm_s390_crypto structure. Lock the + * owner, retrieve the hook function pointer and call the hook. */ + down_read(&vcpu->kvm->arch.crypto.pqap_hook_rwsem); if (vcpu->kvm->arch.crypto.pqap_hook) { - if (!try_module_get(vcpu->kvm->arch.crypto.pqap_hook->owner)) - return -EOPNOTSUPP; - ret = vcpu->kvm->arch.crypto.pqap_hook->hook(vcpu); - module_put(vcpu->kvm->arch.crypto.pqap_hook->owner); + pqap_hook = *vcpu->kvm->arch.crypto.pqap_hook; + ret = pqap_hook(vcpu); if (!ret && vcpu->run->s.regs.gprs[1] & 0x00ff0000) kvm_s390_set_psw_cc(vcpu, 3); + up_read(&vcpu->kvm->arch.crypto.pqap_hook_rwsem); return ret; } + up_read(&vcpu->kvm->arch.crypto.pqap_hook_rwsem); /* * A vfio_driver must register a hook. * No hook means no driver to enable the SIE CRYCB and no queues. @@ -855,10 +873,18 @@ static int handle_stsi(struct kvm_vcpu *vcpu) if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE) return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); - if (fc > 3) { - kvm_s390_set_psw_cc(vcpu, 3); - return 0; - } + /* Bailout forbidden function codes */ + if (fc > 3 && fc != 15) + goto out_no_data; + + /* + * fc 15 is provided only with + * - PTF/CPU topology support through facility 15 + * - KVM_CAP_S390_USER_STSI + */ + if (fc == 15 && (!test_kvm_facility(vcpu->kvm, 11) || + !vcpu->kvm->arch.user_stsi)) + goto out_no_data; if (vcpu->run->s.regs.gprs[0] & 0x0fffff00 || vcpu->run->s.regs.gprs[1] & 0xffff0000) @@ -872,13 +898,13 @@ static int handle_stsi(struct kvm_vcpu *vcpu) operand2 = kvm_s390_get_base_disp_s(vcpu, &ar); - if (operand2 & 0xfff) + if (!kvm_s390_pv_cpu_is_protected(vcpu) && (operand2 & 0xfff)) return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); switch (fc) { case 1: /* same handling for 1 and 2 */ case 2: - mem = get_zeroed_page(GFP_KERNEL); + mem = get_zeroed_page(GFP_KERNEL_ACCOUNT); if (!mem) goto out_no_data; if (stsi((void *) mem, fc, sel1, sel2)) @@ -887,14 +913,23 @@ static int handle_stsi(struct kvm_vcpu *vcpu) case 3: if (sel1 != 2 || sel2 != 2) goto out_no_data; - mem = get_zeroed_page(GFP_KERNEL); + mem = get_zeroed_page(GFP_KERNEL_ACCOUNT); if (!mem) goto out_no_data; handle_stsi_3_2_2(vcpu, (void *) mem); break; + case 15: /* fc 15 is fully handled in userspace */ + insert_stsi_usr_data(vcpu, operand2, ar, fc, sel1, sel2); + trace_kvm_s390_handle_stsi(vcpu, fc, sel1, sel2, operand2); + return -EREMOTE; + } + if (kvm_s390_pv_cpu_is_protected(vcpu)) { + memcpy((void *)sida_origin(vcpu->arch.sie_block), (void *)mem, + PAGE_SIZE); + rc = 0; + } else { + rc = write_guest(vcpu, operand2, ar, (void *)mem, PAGE_SIZE); } - - rc = write_guest(vcpu, operand2, ar, (void *)mem, PAGE_SIZE); if (rc) { rc = kvm_s390_inject_prog_cond(vcpu, rc); goto out; @@ -1084,15 +1119,15 @@ static int handle_pfmf(struct kvm_vcpu *vcpu) if (rc) return rc; - down_read(¤t->mm->mmap_sem); + mmap_read_lock(current->mm); rc = cond_set_guest_storage_key(current->mm, vmaddr, key, NULL, nq, mr, mc); if (rc < 0) { - rc = fixup_user_fault(current, current->mm, vmaddr, + rc = fixup_user_fault(current->mm, vmaddr, FAULT_FLAG_WRITE, &unlocked); rc = !rc ? -EAGAIN : rc; } - up_read(¤t->mm->mmap_sem); + mmap_read_unlock(current->mm); if (rc == -EFAULT) return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING); if (rc == -EAGAIN) @@ -1115,7 +1150,7 @@ static int handle_pfmf(struct kvm_vcpu *vcpu) } /* - * Must be called with relevant read locks held (kvm->mm->mmap_sem, kvm->srcu) + * Must be called with relevant read locks held (kvm->mm->mmap_lock, kvm->srcu) */ static inline int __do_essa(struct kvm_vcpu *vcpu, const int orc) { @@ -1213,9 +1248,9 @@ static int handle_essa(struct kvm_vcpu *vcpu) * already correct, we do nothing and avoid the lock. */ if (vcpu->kvm->mm->context.uses_cmm == 0) { - down_write(&vcpu->kvm->mm->mmap_sem); + mmap_write_lock(vcpu->kvm->mm); vcpu->kvm->mm->context.uses_cmm = 1; - up_write(&vcpu->kvm->mm->mmap_sem); + mmap_write_unlock(vcpu->kvm->mm); } /* * If we are here, we are supposed to have CMMA enabled in @@ -1232,11 +1267,11 @@ static int handle_essa(struct kvm_vcpu *vcpu) } else { int srcu_idx; - down_read(&vcpu->kvm->mm->mmap_sem); + mmap_read_lock(vcpu->kvm->mm); srcu_idx = srcu_read_lock(&vcpu->kvm->srcu); i = __do_essa(vcpu, orc); srcu_read_unlock(&vcpu->kvm->srcu, srcu_idx); - up_read(&vcpu->kvm->mm->mmap_sem); + mmap_read_unlock(vcpu->kvm->mm); if (i < 0) return i; /* Account for the possible extra cbrl entry */ @@ -1244,10 +1279,10 @@ static int handle_essa(struct kvm_vcpu *vcpu) } vcpu->arch.sie_block->cbrlo &= PAGE_MASK; /* reset nceo */ cbrlo = phys_to_virt(vcpu->arch.sie_block->cbrlo); - down_read(&gmap->mm->mmap_sem); + mmap_read_lock(gmap->mm); for (i = 0; i < entries; ++i) __gmap_zap(gmap, cbrlo[i]); - up_read(&gmap->mm->mmap_sem); + mmap_read_unlock(gmap->mm); return 0; } @@ -1432,10 +1467,11 @@ int kvm_s390_handle_eb(struct kvm_vcpu *vcpu) static int handle_tprot(struct kvm_vcpu *vcpu) { - u64 address1, address2; - unsigned long hva, gpa; - int ret = 0, cc = 0; + u64 address, operand2; + unsigned long gpa; + u8 access_key; bool writable; + int ret, cc; u8 ar; vcpu->stat.instruction_tprot++; @@ -1443,45 +1479,48 @@ static int handle_tprot(struct kvm_vcpu *vcpu) if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE) return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP); - kvm_s390_get_base_disp_sse(vcpu, &address1, &address2, &ar, NULL); + kvm_s390_get_base_disp_sse(vcpu, &address, &operand2, &ar, NULL); + access_key = (operand2 & 0xf0) >> 4; - /* we only handle the Linux memory detection case: - * access key == 0 - * everything else goes to userspace. */ - if (address2 & 0xf0) - return -EOPNOTSUPP; if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_DAT) - ipte_lock(vcpu); - ret = guest_translate_address(vcpu, address1, ar, &gpa, GACC_STORE); - if (ret == PGM_PROTECTION) { + ipte_lock(vcpu->kvm); + + ret = guest_translate_address_with_key(vcpu, address, ar, &gpa, + GACC_STORE, access_key); + if (ret == 0) { + gfn_to_hva_prot(vcpu->kvm, gpa_to_gfn(gpa), &writable); + } else if (ret == PGM_PROTECTION) { + writable = false; /* Write protected? Try again with read-only... */ - cc = 1; - ret = guest_translate_address(vcpu, address1, ar, &gpa, - GACC_FETCH); + ret = guest_translate_address_with_key(vcpu, address, ar, &gpa, + GACC_FETCH, access_key); } - if (ret) { - if (ret == PGM_ADDRESSING || ret == PGM_TRANSLATION_SPEC) { - ret = kvm_s390_inject_program_int(vcpu, ret); - } else if (ret > 0) { - /* Translation not available */ - kvm_s390_set_psw_cc(vcpu, 3); + if (ret >= 0) { + cc = -1; + + /* Fetching permitted; storing permitted */ + if (ret == 0 && writable) + cc = 0; + /* Fetching permitted; storing not permitted */ + else if (ret == 0 && !writable) + cc = 1; + /* Fetching not permitted; storing not permitted */ + else if (ret == PGM_PROTECTION) + cc = 2; + /* Translation not available */ + else if (ret != PGM_ADDRESSING && ret != PGM_TRANSLATION_SPEC) + cc = 3; + + if (cc != -1) { + kvm_s390_set_psw_cc(vcpu, cc); ret = 0; + } else { + ret = kvm_s390_inject_program_int(vcpu, ret); } - goto out_unlock; } - hva = gfn_to_hva_prot(vcpu->kvm, gpa_to_gfn(gpa), &writable); - if (kvm_is_error_hva(hva)) { - ret = kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING); - } else { - if (!writable) - cc = 1; /* Write not permitted ==> read-only */ - kvm_s390_set_psw_cc(vcpu, cc); - /* Note: CC2 only occurs for storage keys (not supported yet) */ - } -out_unlock: if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_DAT) - ipte_unlock(vcpu); + ipte_unlock(vcpu->kvm); return ret; } |